© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84332
    Prev
    Next
    INDEX
    Explanations

    yes, no, permission, career

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -1.12
     Oh
    -0.99
     to
    -0.94
     Uh
    -0.93
     especially
    -0.91
     poved
    -0.90
     of
    -0.89
     moreover
    -0.88
     instead
    -0.88
     by
    -0.87
    POSITIVE LOGITS
    ,
    1.23
     sover
    1.05
     sny
    0.98
    DREAM
    0.94
     Nelle
    0.93
     Lombar
    0.92
    YOUNG
    0.92
     JPG
    0.91
    !
    0.90
     nourrir
    0.90
    Activations Density 0.004%

    No Known Activations